Application of artificial neural networks for operating speed prediction at horizontal curves: a case study in Egypt

Horizontal alignment greatly affects the speedof vehicles at rural roads. Therefore, it is necessary toanalyze and predict vehicles speed on curve sections.Numerous studies took rural two-lane as research subjectsand provided models for predicting operating speeds.However, less attention has been paid to multi-lane highwaysespecially in Egypt. In this research, field operatingspeed data of both cars and trucks on 78 curve sections offour multi-lane highways is collected. With the data, correlationbetween operating speed （V85） and alignment isanalyzed. The paper includes two separate relevant analyses.The first analysis uses the regression models toinvestigate the relationships between V85 as dependentvariable, and horizontal alignment and roadway factors asindependent variables. This analysis proposes two predictingmodels for cars and trucks. The second analysisuses the artificial neural networks （ANNs） to explore theprevious relationships. It is found that the ANN modelinggives the best prediction model. The most influential variableon V85 for cars is the radius of curve. Also, for V85 fortrucks, the most influential variable is the median width.Finally, the derived models have statistics within theacceptable regions and they are conceptually reasonable.

Rapid testing and prediction of soil–water characteristic curve of subgrade soils considering stress state and degree of compaction

The subgrade soil is generally in saturated or unsaturated condition. To analyze complex thermo-hydro-mechanical-chemical (THMC) behaviors of subgrade, it is essential to determine the soil–water characteristic curve (SWCC) that represents the relationship between matric suction and moisture content. In this study, a full-automatic rapid stress-dependent SWCC pressure-plate extractor was developed. Then, the influences of overburden stress and degree of compaction on the SWCC of subgrade soil such as high liquid limit silt (MH) and low liquid limit clay (CL) were analyzed. Accordingly, a new model taking into account the influences of overburden stress and degree of compaction based on the well-known Van Genuchten (VG) SWCC fitting model was presented and validated. The results show that with the increase of the degree of compaction and overburden stress, the saturated moisture content of subgrade soil decreases, while the air-entry value increases and the transition section curve becomes flat. The influences of the degree of compaction and overburden stress on the SWCC of MH is greater than that of CL. Meanwhile, there was a satisfactory agreement between the prediction and measurement, indicating a good performance of the new model for predicting the SWCC.

Speed prediction models for car and sports utility vehicleat locations along four-lane median divided horizontal curves

Sites with varying geometric features were analyzed to develop the 85 th percentile speed prediction models for car and sports utility vehicle(SUV) at 50 m prior to the point of curvature(PC), PC, midpoint of a curve(MC), point of tangent(PT) and 50 m beyond PT on four-lane median divided rural highways. The car and SUV speed data were combined in the analysis as they were found to be normally distributed and not significantly different. Independent parameters representing geometric features and speed at the preceding section were logically selected in stepwise regression analyses to develop the models. Speeds at various locations were found to be dependent on some combinations of curve length, curvature and speed in the immediately preceding section of the highway. Curve length had a significant effect on the speed at locations 50 m prior to PC, PC and MC. The effect of curvature on speed was observed only at MC. The curve geometry did not have a significant effect on speed from PT onwards. The speed at 50 m prior to PC and curvature is the most significant parameter that affects the speed at PC and MC, respectively. Before entering a horizontal curve, drivers possibly perceive the curve based on its length. Longer curve encourages drivers to maintain higher speed in the preceding tangent section. Further, drivers start experiencing the effect of curvature only after entering the curve and adjust speed accordingly. Practitioners can use these findings in designing consistent horizontal curve for vehicle speed harmony.

Predicting the entire soil-water characteristic curve using measurements within low suction range

The soil-water characteristic curve(SWCC) is widely used in the design and evaluation in the practice of geotechnical and geoenvironmental engineering such as the slope stability under the influence of environmental factors. The SWCC has distinct features in the capillary and adsorption zones due to different physical mechanisms. Measurements of the SWCC are typically limited within the capillary zone(i.e., low suction range). It is cumbersome and time-consuming to measure the SWCC in the adsorption zone(i.e., high suction range). This study presents a simple method to predict the entire SWCC within both the capillary and adsorption zones, using measured data only from low suction range(e.g., from 0 to 500 kPa). Experimental studies were performed on a completely weathered granite residual soil to determine its entire SWCC from saturated to dry conditions. The resultant SWCC, along with the SWCC measurements of 14 soils reported in the literature, were used to validate the proposed method. The results indicate that the proposed method has good consistency with a wide array of measured data used in this study. The proposed method is easy to use as it only requires a simple parameter calibration for a commonly used SWCC model. It can be used to improve the reliability in the prediction of the SWCC over the entire suction range when measurements are limited within the low suction range.

A Tutorial Review of the Solar Power Curve: Regressions, Model Chains, and Their Hybridization and Probabilistic Extensions

Owing to the persisting hype in pushing toward global carbon neutrality,the study scope of atmospheric science is rapidly expanding.Among numerous trending topics,energy meteorology has been attracting the most attention hitherto.One essential skill of solar energy meteorologists is solar power curve modeling,which seeks to map irradiance and auxiliary weather variables to solar power,by statistical and/or physical means.In this regard,this tutorial review aims to deliver a complete overview of those fundamental scientific and engineering principles pertaining to the solar power curve.Solar power curves can be modeled in two primary ways,one of regression and the other of model chain.Both classes of modeling approaches,alongside their hybridization and probabilistic extensions,which allow accuracy improvement and uncertainty quantification,are scrutinized and contrasted thoroughly in this review.

Research on Optimizing the Hidden Layer Structure of ANN-Based Model and Its Application in Predicting End-Quench Curves of Steels

In this paper, a method of optimizing the number of hidden layer neurons has been put forward. This optimizing method is suitable for three layers B-p network. The purpose of this optimizing method is to reduce the predicting errors when the model is used as predicting model. As an example of application, a predicting model of steel end-quench curves has been designed by using this optimizing method. The result shows that the optimization of ANN hidden layer architecture has an effect on reducing predicting errors.

Development of a new irradiation-embrittlement prediction model for reactor pressure-vessel steels

Predicting the transition-temperature shift(TTS)induced by neutron irradiation in reactor pressure-vessel(RPV)steels is important for the evaluation and extension of nuclear power-plant lifetimes.Current prediction models may fail to properly describe the embrittlement trend curves of Chinese domestic RPV steels with relatively low Cu content.Based on the screened surveillance data of Chinese domestic and similar international RPV steels,we have developed a new fluencedependent model for predicting the irradiation-embrittlement trend.The fast neutron fluence(E>1 MeV)exhibited the highest correlation coefficient with the measured TTS data;thus,it is a crucial parameter in the prediction model.The chemical composition has little relevance to the TTS residual calculated by the fluence-dependent model.The results show that the newly developed model with a simple power-law functional form of the neutron fluence is suitable for predicting the irradiation-embrittlement trend of Chinese domestic RPVs,regardless of the effect of the chemical composition.

An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method

Properties prediction of crude oil remains an essential issue for refineries. In this communication, an exhaustive and extendable support vector machine(SVM) intelligent prediction process has been proposed to solve this problem. A novel hybrid genetic algorithm-particle swarm optimization(GA-PSO)method was applied to optimize the SVM model. The optimization process and result demonstrated that the newly proposed GA-PSO-SVM method was more accurate and time-saving than the classical GA or PSO method. Compared with the classical Grid-search SVM, the combined GA-PSO-SVM model appeared to be more applicable for the properties prediction task. The TBP distillation curve fitting was exampled to evaluate the performance of the developed model. The regression result demonstrated the high accuracy and efficiency of the proposed process. The model can be applied in the Industrial Internet as a plugin, and the adaptability and flexibility is demonstrated by the implement of crude oil molecular reconstruction employing the intelligent prediction process.

New Computer-aided Method for Optimum Use and Properties Prediction of Steels

When selecting a steel grade, a quenching medium or heat treating parameters for a given steel part, their applicability depends on whether the microstructures and properties at the specified position of the cross-section satisfy the specific application requirements. Based on steel hardenability elements, charts of equivalent cooling rates as well as object-oriented programming methods, a computerized method is developed. In addition, this paper has studied the prediction of mechanical properties and microstructures of the as-quenched parts. It is also studied that the prediction of ideal critical diameter and Jominy curve from chemical composition on the basis of ASTM A255.

Determination of ultimate bearing capacity of uplift piles using intact and non-intact load−displacement curve

Based on the field destructive test of six rock-socketed piles with shallow overburden,three prediction models are used to quantitatively analyze and predict the intact load−displacement curve.The predicted values of ultimate uplift capacity were further determined by four methods(displacement controlling method(DCM),reduction coefficient method(RCM),maximum curvature method(MCM),and critical stiffness method(CSM))and compared with the measured value.Through the analysis of the relationship between the change rate of pullout stiffness and displacement,a method used to determine the ultimate uplift capacity via non-intact load−displacement curve was proposed.The results show that the predicted value determined by DCM is more conservative,while the predicted value determined by MCM is larger than the measured value.This suggests that RCM and CSM in engineering applications can be preferentially applied.Moreover,the development law of the change rate of pullout stiffness with displacement agrees well with the attenuation form of power function.The theoretical predicted results of ultimate uplift capacity based on the change rate of pullout stiffness will not be affected by the integrity of the curve.The method is simple and applicable for the piles that are not loaded to failure state,and thus provides new insights into ultimate uplift capacity determination of test piles.

A novel type curve for estimating oil recovery factor of gas flooding

A novel type curve is presented for oil recovery factor prediction suitable for gas flooding by innovatively introducing the equivalent water-gas cut to replace the water cut,comprehensively considering the impact of three-phase flow(oil,gas,water),and deriving the theoretical equations of gas flooding type curve based on Tong’s type curve.The equivalent water-gas cut is the ratio of the cumulative underground volume of gas and water production to the total underground volume of produced fluids.Field production data and the numerical simulation results are used to demonstrate the feasibility of the new type curve and verify the accuracy of the prediction results with field cases.The new type curve is suitable for oil recovery factor prediction of both water flooding and gas flooding.When a reservoir has no gas injected or produced,the gas phase can be ignored and only the oil and water phases need to be considered,in this case,this gas flooding type curve returns to the Tong’s type curve,which can evaluate the oil recovery factor of water flooding.For reservoirs with equivalent water-gas cuts of 60%-80%,the regression method of the new type curve works well in predicting the oil recovery factor.For reservoirs with equivalent water-gas cuts higher than 80%,both the regression and assignment methods of the new type curve can accurately predict the oil recovery factor of gas flooding.

Vibration Fatigue Probabilistic Life Prediction Model and Method for Blade

Vibration fatigue is one of the main failure modes of blade.The vibration fatigue life of blade is scattered caused by manufacture error,material property dispersion and external excitation randomness.A new vibration fatigue probabilistic life prediction model(VFPLPM)and a prediction method are proposed in this paper.Firstly,as one-dimensional volumetric method(ODVM)only considers the principle calculation direction,a three-dimensional space vector volumetric method(TSVVM)is proposed to improve fatigue life prediction accuracy for actual threedimensional engineering structure.Secondly,based on the two volumetric methods(ODVM and TSVVM),the material C-P-S-N fatigue curve model(CFCM)and the maximum entropy quantile function model(MEQFM),VFPLPM is established to predict the vibration fatigue probabilistic life of blade.The VFPLPM is combined with maximum stress method(MSM),ODVM and TSVVM to estimate vibration fatigue probabilistic life of blade simulator by finite element simulation,and is verified by vibration fatigue test.The results show that all of the three methods can predict the vibration fatigue probabilistic life of blade simulator well.VFPLPM &TSVVM method has the highest computational accuracy for considering stress gradient effect not only in the principle calculation direction but also in other space vector directions.

Application of New Water Flooding Characteristic Curve in the High Water-Cut Stage of an Oilfield

The oil production predicted by means of the conventional water-drive characteristic curve is typically affected by large deviations with respect to the actual value when the so-called high water-cut stage is entered.In order to solve this problem,a new characteristic relationship between the relative permeability ratio and the average water saturation is proposed.By comparing the outcomes of different matching methods,it is verified that it can well reflect the variation characteristics of the relative permeability ratio curve.Combining the new formula with a reservoir engineering method,two new formulas are derived for the water flooding characteristic curve in the high water-cut stage.Their practicability is verified by using the production data of Mawangmiao and Xijiakou blocks.The results show that the error between the predicted cumulative oil production and production data of the two new water drive characteristic curves is less than the error between the B-type water drive characteristic curve and the other two water drive characteristic curves.It is concluded that the two new characteristic curves can be used to estimate more accurately the recoverable reserves,the final recovery and to estimate the effects of water flooding.

IMPROVEMENT OF THE PLOT METHOD OF FATIGUE LIFE PREDICTION FORMULA

The fatigue life for components can be predicted by the plot method which is easy and convenient in engineering. Based on the usual fatigue life prediction formula, a new formula for estimating the low stress and high cycle fatigue life is proposed and deduced, which has adopted more accurate SN curve relationship——WeibullSN curve formula. The solution of the new formula is given, too. In addition, an example has been calculated and proved in practice. The results of the new formula and the old one are given and compared.

Prediction of Antifrccze Critical Strength of Infant Age Concrete

The rule of infant age concrete strength development under low temperature and complex affecting factors is researched. An efficient and reliable mathematical forecast model is set up to predict the infant age concrete antifreeze critical strength under low temperature at construction site. On the basis of the revision of concrete equivalent coefficient under complex influencing factors, least-squares curve-fitting method is applied to approximate the concrete strength under standard curing and the forecast formula of concrete compressive strength could be obtained under natural temperature condition by various effects. When the amounts of double-doped are 10% fly ashes and 4% silica fumes as coment replacement, the antifreeze critical strength changes form 3.5-4.1MPa under different low temperature curing. The equivalent coefficient correction formula of concrete under low temperature affected by various factors could be obtained. The obtained equivalent coefficient is suitable for calculating the strength which is between 10% to 40% of standard strength and the curing temperature from 5-20 ℃. The forecast value of concrete antifreeze critical strength under low temperature could be achieved by combining the concrete antifreeze critical strength value with the compressive strength forecast of infant age concrete under low temperature. Then the theory for construction quality control under low temperature is provided.

An Early Stopping-Based Artificial Neural Network Model for Atmospheric Corrosion Prediction of Carbon Steel

The optimization of network topologies to retain the generalization ability by deciding when to stop overtraining an artificial neural network(ANN)is an existing vital challenge in ANN prediction works.The larger the dataset the ANN is trained with,the better generalization the prediction can give.In this paper,a large dataset of atmospheric corrosion data of carbon steel compiled from several resources is used to train and test a multilayer backpropagation ANN model as well as two conventional corrosion prediction models(linear and Klinesmith models).Unlike previous related works,a grid search-based hyperparameter tuning is performed to develop multiple hyperparameter combinations(network topologies)to train multiple ANNs with mini-batch stochastic gradient descent optimization algorithm to facilitate the training of a large dataset.After that,one selection strategy for the optimal hyperparameter combination is applied by an early stopping method to guarantee the generalization ability of the optimal network model.The correlation coefficients(R)of the ANN model can explain about 80%(more than 75%)of the variance of atmospheric corrosion of carbon steel,and the root mean square errors(RMSE)of three models show that the ANN model gives a better performance than the other two models with acceptable generalization.The influence of input parameters on the output is highlighted by using the fuzzy curve analysis method.The result reveals that TOW,Cl-and SO2 are the most important atmospheric chemical variables,which have a well-known nonlinear relationship with atmospheric corrosion.

Threshold Selection Study on Fisher Discriminant Analysis Used in Exon Prediction for Unbalanced Data Sets

In gene prediction, the Fisher discriminant analysis (FDA) is used to separate protein coding region (exon) from non-coding regions (intron). Usually, the positive data set and the negative data set are of the same size if the number of the data is big enough. But for some situations the data are not sufficient or not equal, the threshold used in FDA may have important influence on prediction results. This paper presents a study on the selection of the threshold. The eigen value of each exon/intron sequence is computed using the Z-curve method with 69 variables. The experiments results suggest that the size and the standard deviation of the data sets and the threshold are the three key elements to be taken into consideration to improve the prediction results.

Analysis and Prediction of Residents' Income Gap in Poverty-stricken Areas of Yunnan Province

Taking Ludian County in Zhaotong City of Yunnan Province for example,according to the data on residents'income gap in Ludian County during the period 2002-2011,we analyze the residents'income gap in Ludian County,and offer the forecast value of residents'income gap in Ludian County during the period 2012-2015,using Compertz curve model and Eviews software for fitting.The forecast value shows that the residents'income gap will continue to widen in Ludian County.Finally we put forth the recommendations for bridging the residents'income gap in Ludian County,in order to provide a reference for settling the problems concerning residents'income gap in other state-level povertystricken counties of Yunnan Province.

Application of Support Vector Machine to Predict 5-year Survival Status of Patients with Nasopharyngeal Carcinoma after Treatment

Objective： Support Vector Machine （SVM） is a machine-learning method, based on the principle of structural risk minimization, which performs well when applied to data outside the training set. In this paper, SVM was applied to predict 5-year survival status of patients with nasopharyngeal carcinoma （NPC） after treatment, we expect to find a new way for prognosis studies in cancer so as to assist right clinical decision for individual patient. Methods： Two modelling methods were used in the study; SVM network and a standard parametric logistic regression were used to model 5-year survival status. And the two methods were compared on a prospective set of patients not used in model construction via receiver operating characteristic （ROC） curve analysis. Results： The SVM1, trained with the 25 original input variables without screening, yielded a ROC area of 0.868, at sensitivity to mortality of 79.2% and the specificity of 94.5%. Similarly, the SVM2, trained with 9 input variables which were obtained by optimal input variable selection from the 25 original variables by logistic regression screening, yielded a ROC area of 0.874, at a sensitivity to mortality of 79.2% and the specificity of 95.6%, while the logistic regression yielded a ROC area of 0.751 at a sensitivity to mortality of 66.7% and gave a specificity of 83.5%. Conclusion： SVM found a strong pattern in the database predictive of 5-year survival status. The logistic regression produces somewhat similar, but better, results. These results show that the SVM models have the potential to predict individual patient＇s 5-year survival status after treatment, and to assist the clinicians for making a good clinical decision.

Prediction of forming limit curve(FLC) for Al–Li alloy 2198-T3 sheet using diferent yield functions

The Forming Limit Curve （FLC） of the third generation aluminum-lithium （Al-Li） alloy 2198-T3 is measured by conducting a hemispherical dome test with specimens of different widths. The theoretical prediction of the FLC of 2198-T3 is based on the M-K theory utilizing respectively the von Mises, Hill＇48, Hosford and Barlat 89 yield functions, and the different predicted curves due to different yield functions are compared with the experimentally measured FLC of 2198-T3. The results show that though there are differences among the four predicted curves, yet they all agree well with the experimentally measured curve. In the area near the planar strain state, the predicted curves and experimentally measured curve are very close. The predicted curve based on the Hosford yield function is more accurate under the tension-compression strain states described in the left part of the FLC, while the accuracy is better for the predicted curve based on Hill＇48 yield function under the tension-tension strain states shown in the right part.